Abstract

Machine learning-based activity and gait phase recognition algorithms are used in powered motion assistive devices to inform control of motorized components. The objective of this study was to develop a supervised multiclass classifier to simultaneously detect activity and gait phase (stance, swing) in real-world walking, stair ascent, and stair descent using inertial measurement data from the thigh and shank. The intended use of this algorithm was for control of a motion assistive device local to the knee. Using data from 80 participants, two decision trees and five long short-term memory (LSTM) models that each used different feature sets were initially tested and evaluated using a novel performance metric: proportion of perfectly classified strides (PPCS). Based on the PPCS of these initial models, five additional posthoc LSTM models were tested. Separate models were developed to classify (i) both activity and gait phase simultaneously (one model predicting six states), and (ii) activity-specific models (three individual binary classifiers predicting stance/swing phases). The superior activity-specific model had an accuracy of 98.0% and PPCS of 55.7%. The superior six-phase model used filtered inertial measurement data as its features and a median filter on its predictions and had an accuracy of 92.1% and PPCS of 22.9%. Pooling stance and swing phases from all activities and treating this model as a binary classifier, this model had an accuracy of 97.1%, which may be acceptable for real-world lower limb exoskeleton control if only stance and swing gait phases must be detected. Keywords: machine learning, deep learning, inertial measurement unit, activity recognition, gait.

References

1.
Simon
,
S. R.
,
2004
, “
Quantification of Human Motion: Gait Analysis – Benefits and Limitations to Its Applications and Clinical Problems
,”
J. Biomech.
,
37
(
12
), pp.
1869
1880
.10.1016/j.jbiomech.2004.02.047
2.
Kang
,
I.
,
Kunapuli
,
P.
, and
Young
,
A. J.
,
2020
, “
Real-Time Neural Network-Based Gait Phase Estimation Using a Robotic Hip Exoskeleton
,”
IEEE Trans. Med. Rob. Bionics
,
2
(
1
), pp.
28
37
.10.1109/TMRB.2019.2961749
3.
Dutta
,
A.
,
Ma
,
O.
,
Toledo
,
M.
,
Pregonero
,
A. F.
,
Ainsworth
,
B. E.
,
Buman
,
M. P.
, and
Bliss
,
D. W.
,
2018
, “
Identifying Free-Living Physical Activities Using Lab-Based Models With Wearable Accelerometers
,”
Sensors
,
18
(
11
), p.
3893
.10.3390/s18113893
4.
McFadyen
,
B. J.
, and
Winter
,
D. A.
,
1988
, “
An Integrated Biomechanical Analysis of Normal Stair Ascent and Descent
,”
J. Biomech.
,
21
(
9
), pp.
733
744
.10.1016/0021-9290(88)90282-5
5.
Manchola
,
M. D.
,
Sanchez
,
M. J. P.
,
Munera
,
M.
, and
Cifuentes
,
C. A.
,
2019
, “
Gait Phase Detection for Lower-Limb Exoskeletons Using Foot Motion Data From a Single Inertial Measurement Unit in Hemiparetic Individuals
,”
Sensors
,
19
(
13
), p.
2988
.10.3390/s19132988
6.
Liu
,
M.
,
Zhang
,
F.
, and
Huang
,
H.
,
2017
, “
An Adaptive Classification Strategy for Reliable Locomotion Mode Recognition
,”
Sensors
,
17
(
9
), pp.
2
18
.10.3390/s17092020
7.
De Luca
,
C. J.
,
1997
, “
The Use of Surface Electromyography in Biomechanics
,”
J. Appl. Biomech.
,
13
(
2
), pp.
135
163
.10.1123/jab.13.2.135
8.
Vu
,
H. T.
,
Dong
,
D.
,
Cao
,
H.-L.
,
Verstraten
,
T.
,
Lefeber
,
D.
,
Vanderborght
,
B.
, and
Geeroms
,
J.
,
2020
, “
A Review of Gait Phase Detection Algorithms for Lower Limb Prostheses
,”
Sensors
,
20
(
14
), pp.
1
19
.10.3390/s20143972
9.
Evans
,
R. L.
, and
Arvind
,
D. K.
,
2014
, “
Detection of Gait Phases Using Orient Specks for Mobile Clinical Gait Analysis
,”
Proceedings of 11th International Conference on Wearable and Implantable Body Sensor Networks
,
Eindhoven, The Netherlands
, June 16–19, pp.
149
154
.10.1109/BSN.2014.22
10.
Martinez
,
A.
,
Lawson
,
B.
, and
Goldfarb
,
M.
,
2017
, “
Preliminary Assessment of a Lower-Limb Exoskeleton Controller for Guiding Leg Movement in Overground Walking
,”
Proceedings of 40th International Conference of the IEEE Engineering in Medicine and Biology Society
, Honolulu, HI, July 17–21, pp.
279
2800
.10.1109/ICORR.2017.8009276
11.
Mannini
,
A.
, and
Sabatini
,
A. M.
,
2012
, “
Gait Phase Detection and Discrimination Between Walking-Jogging Activities Using Hidden Markov Models Applied to Foot Motion Data From a Gyroscope
,”
Gait Posture
,
36
(
4
), pp.
657
661
.10.1016/j.gaitpost.2012.06.017
12.
Martinez-Hernandez
,
U.
,
Mahmood
,
I.
, and
Dehghani-Sanij
,
A. A.
,
2018
, “
Simultaneous Bayesian Recognition of Locomotion and Gait Phases With Wearable Sensors
,”
IEEE Sens. J.
,
18
(
3
), pp.
1282
1290
.10.1109/JSEN.2017.2782181
13.
Khera
,
P.
, and
Kumar
,
N.
,
2020
, “
Role of Machine Learning in Gait Analysis: A Review
,”
J. Med. Eng. Technol.
,
44
(
8
), pp.
441
467
.10.1080/03091902.2020.1822940
14.
Dolatabadi
,
E.
,
Taati
,
B.
, and
Mihailidis
,
A.
,
2017
, “
An Automated Classification of Pathological Gait Using Unobtrusive Sensing Technology
,”
IEEE Trans. Neural Syst. Rehabil. Eng.
,
25
(
12
), pp.
2336
2346
.10.1109/TNSRE.2017.2736939
15.
Ramasamy Ramamurthy
,
S.
, and
Roy
,
N.
,
2018
, “
Recent Trends in Machine Learning for Human Activity Recognition – A Survey
,”
Wiley Interdiscip. Rev.: Data Min. Knowl. Disc.
,
8
(
4
), pp.
1
11
.10.1002/widm.1254
16.
Zhao
,
H.
,
Wang
,
Z.
,
Qiu
,
S.
,
Wang
,
J.
,
Xu
,
F.
,
Wang
,
Z.
, and
Shen
,
Y.
,
2019
, “
Adaptive Gait Detection Based on Foot-Mounted Inertial Sensors and Multi-Sensor Fusion
,”
Inf. Fusion
,
52
, pp.
157
166
.10.1016/j.inffus.2019.03.002
17.
Farah
,
J. D.
,
Baddour
,
N.
, and
Lemaire
,
E. D.
,
2019
, “
Design, Development, and Evaluation of a Local Sensor-Based Gait Phase Recognition System Using a Logistic Model Decision Tree for Orthosis-Control
,”
J. NeuroEng. Rehabil.
,
16
(
1
), pp.
1
11
.10.1186/s12984-019-0486-z
18.
Lawton
,
M. P.
, and
Brody
,
E. M.
,
1969
, “
Assessment of Older People: Self-Maintaining and Instrumental Activities of Daily Living
,”
Gerontologist
,
9
(
3 Part 1
), pp.
179
186
.10.1093/geront/9.3_Part_1.179
19.
Brodie
,
M. A. D.
,
Coppens
,
M. J. M.
,
Lord
,
S. R.
,
Lovell
,
N. H.
,
Gschwind
,
Y. J.
,
Redmond
,
S. J.
,
Del Rosario
,
M. B.
,
Wang
,
K.
,
Sturnieks
,
D. L.
,
Persiani
,
M.
, and
Delbaere
,
K.
,
2016
, “
Wearable Pendant Device Monitoring Using New Wavelet-Based Methods Shows Daily Life and Laboratory Gaits Are Different
,”
Med. Biol. Eng. Comput.
,
54
(
4
), pp.
663
674
.10.1007/s11517-015-1357-9
20.
Hora
,
M.
,
Soumar
,
L.
,
Pontzer
,
H.
, and
Sladek
,
V.
,
2017
, “
Body Size and Lower Limb Posture During Walking in Humans
,”
PLoS One
,
12
(
2
), pp.
e0172112
e0172126
.10.1371/journal.pone.0172112
21.
Bauman
,
V.
,
2021
, “
Activity and Gait Phase Recognition for Walking, Stair Ascent, and Stair Descent
,”
M.A.Sc. thesis
,
School of Engineering, University of Guelph
, Guelph, ON, Canada.https://atrium.lib.uoguelph.ca/xmlui/bitstream/handle/10214/26320/Bauman_Valerie_202108_MASc.pdf?sequence=4
22.
Ding
,
Z.
,
Yang
,
C.
,
Xing
,
K.
,
Ma
,
X.
,
Yang
,
K.
,
Guo
,
H.
,
Yi
,
C.
, and
Jiang
,
F.
,
2018
, “
The Real Time Gait Phase Detection Based on Long Short-Term Memory
,”
Proceedings of Third IEEE International Conference on Data Science in Cyberspace
, Guangzhou, China, June 18–21.10.1109/DSC.2018.00014
23.
Sun
,
W.
,
Ding
,
W.
,
Yan
,
H.
, and
Duan
,
S.
,
2018
, “
Zero Velocity Interval Detection Based on a Continuous Hidden Markov Model in Micro Inertial Pedestrian Navigation
,”
Meas. Sci. Technol.
,
29
(
6
), pp.
065103
–065
121007
.10.1088/1361-6501/aab59d
24.
Daud
,
W. M. B. W.
,
Yahya
,
A. B.
,
Horng
,
C. S.
,
Sulaima
,
M. F.
, and
Sudirman
,
R.
,
2013
, “
Features Extraction of Electromyography Signals in Time Domain on Biceps Brachii Muscle
,”
Int. J. Model. Optim.
,
3
(
6
), pp.
515
519
.10.7763/IJMO.2013.V3.332
25.
Yang
,
J.
,
Huang
,
T.-H.
,
Yu
,
S.
,
Yang
,
X.
,
Su
,
H.
,
Spungen
,
A. M.
, and
Tsai
,
C.-Y.
,
2019
, “
Machine Learning Based Adaptive Gait Phase Estimation Using Inertial Measurement Sensors
,”
ASME
Paper No. DMD2019-3266.10.1115/DMD2019-3266
26.
Kreuzer
,
D.
, and
Munz
,
M.
,
2021
, “
Deep Convolutional and LSTM Networks on Multi-Channel Time Series Data for Gait Phase Recognition
,”
Sensors
,
21
(
3
), p.
789
.10.3390/s21030789
27.
Zhen
,
T.
,
Yan
,
L.
, and
Yuan
,
P.
,
2019
, “
Walking Gait Phase Detection Based on Acceleration Signals Using LSTM-DNN Algorithm
,”
Algorithms
,
12
(
12
), p.
253
.10.3390/a12120253
28.
Parvandeh
,
S.
,
Yeh
,
H.-W.
,
Paulus
,
M. P.
, and
McKinney
,
B. A.
,
2020
, “
Consensus Features Nested Cross-Validation
,”
Bioinformatics
,
36
(
10
), pp.
3093
3098
.10.1093/bioinformatics/btaa046
29.
Goodfellow
,
I.
,
Bengio
,
Y.
, and
Courville
,
A.
,
2016
,
Deep Learning
,
MIT Press
,
Cambridge, MA
.
30.
Ferrari
,
A.
,
Micucci
,
D.
,
Mobilio
,
M.
, and
Napoletano
,
P.
,
2020
, “
On the Personalization of Classification Models for Human Activity Recognition
,”
IEEE Access
,
8
, pp.
32066
32079
.10.1109/ACCESS.2020.2973425
31.
Dehzangi
,
O.
,
Taherisadr
,
M.
, and
Vala
,
R. C.
,
2017
, “
IMU-Based Gait Recognition Using Convolutional Neural Networks and Multi-Sensor Fusion
,”
Sensors
,
17
(
12
), p.
2735
.10.3390/s17122735
32.
Di Nardo
,
F.
,
Morbidoni
,
C.
,
Cucchiarelli
,
A.
, and
Fioretti
,
S.
,
2020
, “
Recognition of Gait Phases With a Single Knee Electrogoniometer: A Deep Learning Approach
,”
Electronics
,
9
(
2
), p.
355
.10.3390/electronics9020355
33.
Zhang
,
M.
,
Liu
,
X.
,
Wang
,
W.
,
Gao
,
J.
, and
He
,
Y.
,
2018
, “
Navigating With Graph Representations for Fast and Scalable Decoding of Neural Language Models
,”
32nd International Conference on Neural Information Processing Systems
, Montreal, ON, Canada, Dec. 3–8, pp.
1
2
.https://proceedings.neurips.cc/paper/2018/file/366f0bc7bd1d4bf414073cabbadfdfcd-Paper.pdf
34.
Jung
,
J.-Y.
,
Heo
,
W.
,
Yang
,
H.
, and
Park
,
H.
,
2015
, “
A Neural Network-Based Gait Phase Classification Method Using Sensors Equipped on Lower Limb Exoskeleton Robots
,”
Sensors
,
15
(
11
), pp.
27738
27759
.10.3390/s151127738
35.
Mannini
,
A.
,
Genovese
,
V.
, and
Sabatin
,
A. M.
,
2014
, “
Online Decoding of Hidden Markov Models for Gait Event Detection Using Foot-Mounted Gyroscopes
,”
IEEE J. Biomed. Health Inf.
,
18
(
4
), pp.
1122
1130
.10.1109/JBHI.2013.2293887
36.
Vargas-Valencia
,
L. S.
,
Elias
,
A.
,
Rocon
,
E.
,
Bastos-Filho
,
T.
, and
Frizera
,
A.
,
2016
, “
An IMU-to-Body Alignment Method Applied to Human Gait Analysis
,”
Sensors (Basel)
,
16
(
12
), p.
2090
.10.3390/s16122090
You do not currently have access to this content.